Video-based Face Recognition (VFR) can be converted to the matching of two image sets containing face images captured from each video. For this purpose, we propose to bridge the two sets with a reference image set tha...
详细信息
Video-based Face Recognition (VFR) can be converted to the matching of two image sets containing face images captured from each video. For this purpose, we propose to bridge the two sets with a reference image set that is well-defined and pre-structured to a number of local models offline. In other words, given two image sets, as long as each of them is aligned to the reference set, they are mutually aligned and well structured. Therefore, the similarity between them can be computed by comparing only the corresponded local models rather than considering all the pairs. To align an image set with the reference set, we further formulate the problem as a quadratic programming. It integrates three constrains to guarantee robust alignment, including appearance matching cost term exploiting principal angles, geometric structure consistency using affine invariant reconstruction weights, smoothness constraint preserving local neighborhood relationship. Extensive experimental evaluations are performed on three databases: Honda, MoBo and YouTube. Compared with competing methods, our approach can consistently achieve better results.
Swarm intelligence is an umbrella for amount optimization algorithms. This discipline deals with natural and artificial systems composed of many individuals that coordinate their activities using decentralized control...
详细信息
The wide application of General Purpose Graphic Processing Units (GPGPUs) results in large manual efforts on porting and optimizing algorithms on them. However, most existing automatic ways of generating GPGPU code fa...
详细信息
computer-supported collaborative learning (CSCL) is an emerging branch of learning science concerned with studying how people can learn together with the help of computers. As an indispensable ingredient, computer med...
详细信息
With further development and wide acceptance of cloud computing, lots of companies and colleges decide to take advantage of it in their own data centers, which is known as private clouds. Since private clouds have som...
详细信息
Sensor nodes in wireless networks often use batteries as their source of energy, but replacing or recharging exhausted batteries in a deployed network can be difficult and costly. Therefore, prolonging battery life be...
详细信息
Sensor nodes in wireless networks often use batteries as their source of energy, but replacing or recharging exhausted batteries in a deployed network can be difficult and costly. Therefore, prolonging battery life becomes a principal objective in the design of wireless sensor networks (WSNs). There is little published data that quantitatively analyze a sensor node's lifetime under different operating conditions. This paper presents several experiments to quantify the impact of key wireless sensor network design and environmental parameters on battery performance. Our testbed consists of MicaZ motes, commercial alkaline batteries, and a suite of techniques for measuring battery performance. We evaluate known parameters, such as communication distance, working channel and operating power that play key roles in battery performance. Through extensive real battery discharge measurements, we expect our results to serve as a quantitative basis for future research in designing and implementing battery-efficient sensing applications and protocols.
Instruction-level redundancy is an effective scheme to reduce the susceptibility of microprocessors to soft errors, offering high error detection and recovery capability;however, it usually incurs significant performa...
详细信息
ISBN:
(纸本)9781467344975
Instruction-level redundancy is an effective scheme to reduce the susceptibility of microprocessors to soft errors, offering high error detection and recovery capability;however, it usually incurs significant performance degradation due to resource racing. Motivated by the fact that narrow-width operands are commonly seen in applications, we exploit data-level parallelism to accelerate instruction-level redundancy. For the instructions within sphere of replication (SoR) of data-level redundancy, normal and redundant versions of the narrow-width operand of the instruction are folded into one register to share the same functional unit during execution hence alleviating resource racing. The other instructions are all protected by instructionlevel redundancy. We run SPECint2000 benchmarks on a modified version of SimpleScalar simulator, and synthesize the extra hardware to evaluate area overhead of the proposed pipeline. Experimental results show that our acceleration scheme outperforms conventional instruction-level redundancy by 13% in IPC. Besides, the extra area overhead is negligible.
We propose an approach to recognize group activities which involve several persons based on modeling the interactions between human bodies. Benefitted from the recent progress in pose estimation [1], we model the acti...
详细信息
We propose an approach to recognize group activities which involve several persons based on modeling the interactions between human bodies. Benefitted from the recent progress in pose estimation [1], we model the activities as the interactions between the parts belong to the same person (intra-person) and those between the parts of different persons (inter-person). Then a unified, discriminative model which integrates both types of interactions is developed. The experiments on the UT-Interaction Dataset [2] show the promising results and demonstrate the power of the interacting models.
Cloud computing is a new computing model. The resource monitoring tools are immature compared to traditional distributed computing and grid computing. In order to better monitor the virtual resource in cloud computing...
详细信息
Cloud computing is a new computing model. The resource monitoring tools are immature compared to traditional distributed computing and grid computing. In order to better monitor the virtual resource in cloud computing, a periodically and event-driven push (PEP) monitoring model is proposed. Taking advantage of the push and event-driven mechanism, the model can provide comparatively adequate information about usage and status of the resources. It can simplify the communication between Master and Work Nodes without missing the important issues happened during the push interval. Besides, we develop "mon" to make up for the deficiency of Libvirt in monitoring of virtual CPU and memory.
Moore's law continues to grant computer architects ever more transistors in the foreseeable future, and para-llelism is the key to continued performance scaling in modern microprocessors. In this paper, the achiev...
详细信息
暂无评论